Dr.S.Athinarayanan

@veltech.edu.in

Associate Professor, Department of CSE, School of Computing.
Veltech Rangarajan Dr.Sakunthala R & D Institute of Science and Technology Deemed to be University

Dr.S.Athinarayanan


               Download Compact PDF  
https://researchid.co/aathithe

EDUCATION

Doctorate holder

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Computer Vision and Pattern Recognition, Artificial Intelligence, Computer Science Applications
29

Scopus Publications

Scopus Publications

  • TRANSFER LEARNING-DRIVEN DEEP NEURAL NETWORK FRAMEWORK FOR EARLY AND ACCURATE BREAST CANCER DETECTION
    D.B Shanmugam, S. Athinarayanan, A. Josephine Christilda, G. Manoharan
    Kufa Journal of Engineering, 2026
    Breast cancer continues to be one of the world’s leading causes of death for women and early detection is essential to increasing survival rates and simplifying treatment. Even though they work well traditional diagnostic methods frequently require a lot of time and resources and are prone to human interpretation errors. Although training deep neural networks from scratch requires large-scale annotated datasets which are frequently unavailable in medical domains recent developments in deep learning have demonstrated great promise in medical image analysis. This work suggests a Transfer Learning-Driven Deep Neural Network Framework for early and precise breast cancer detection in order to overcome this difficulty. The framework makes use of pre-trained convolutional neural network (CNN) architectures that have been refined on publicly accessible mammography and histopathological datasets including VGG19 ResNet and DenseNet. To improve model generalization and lessen overfitting extensive preprocessing procedures like image normalization noise reduction and data augmentation are used. The suggested method outperforms traditional CNNs trained from scratch with accuracy exceeding 97% precision and recall above 96% and an F1-score of 0. 97 according to experimental evaluations on benchmark datasets like BreakHis and CBIS-DDSM. The findings demonstrate how transfer learning can enable reliable data-efficient breast cancer detection systems opening the door for clinical applications with limited resources and real-time capabilities
  • NEDI: An Interpretable Neural Energy Framework for EEG-Based Discrimination of Alzheimer's and Frontotemporal Dementia
    Kavitha Shanmugakani, S. Athinarayanan, Kavitha Shanmugakani
    2026 International Conference on Recent Advances in Electrical Electronics Ubiquitous Communication and Computational Intelligence Raeeucci 2026, 2026
    Clinically distinguishing Alzheimer's disease (AD) from frontotemporal dementia (FTD) is often difficult, especially if only non-invasive electrophysiological signals are available for diagnosis. Electroencephalography (EEG) is able to measure global brain activity with fine-grained temporal resolution, however spectral and entropy-based EEG biomarkers have been shown to lack specificity for certain classes of neurodegenerative diseases limiting clinical interpretability. This assesses a composite EEG metric designed to quantify changes in neural energy metabolism, called the Neural Energy Decline Index (NEDI). NEDI aggregates BLPA, EAEL, and SCA into a weighted scalar, normalized per-subject to limit inter-subject bias and information leakage. This approach tests the discriminability of NEDI between AD and FTD patients using clinically matched cohorts along with interpretable machine-learning classifiers and nested, stratified cross-validation. NEDI demonstrates separability with smaller values associated with AD vs FTD, resulting in a medium to large effect size (Cohen's <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{d}=\mathbf{2. 9 8}$</tex>) between groups. The largest effect was seen using a shallow hybrid ensemble classifier with accuracy 0.901, AUC <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$=0.920$</tex>. According to these results, NEDI represents significant variations in EEG activity based upon the diseases. In addition, this study suggests that disease-specific differences are identified using energy-based EEG features rather than those commonly used.
  • Intelligent Diagnostic Framework for Pneumoconiosis
    S Athinarayanan, K. Likhitha, V. Naga Prathyusha
    2026 International Conference on Communication Computing and Emerging Technologies Ic3et 2026, 2026
  • Advancing Diabetic Retinopathy Screening With DR-NetFusion: A Hybrid Deep Learning Model for Enhanced Detection and Interpretability
    Sunder R., V. Saravana Kumar, Kavitha M., S. Athinarayanan, Umesh Kumar Lilhore, Sarita Simaiya, Lidia Gosy Tekeste, Shimaa A. Hussien, Ehab Seif Ghith
    Complexity, 2026
    Diabetic retinopathy (DR) is one of the leading causes of preventable blindness worldwide, making timely and accurate detection crucial for effective management. This study introduces DR‐NetFusion, a novel hybrid deep learning framework designed to automate DR detection and classification. The proposed model synergistically combines convolutional neural networks (CNNs) and transformer architectures, leveraging the strengths of both in capturing local features and global context from retinal images. DR‐NetFusion performs multiscale feature extraction, integrates a dual‐attention mechanism, and incorporates ensemble learning to improve robustness and model performance. Additionally, the framework utilizes generative adversarial networks (GANs) for synthetic data augmentation to address data scarcity challenges and applies pretrained transfer learning to enhance efficiency. For interpretability, we incorporate Grad‐CAM and SHAP techniques, providing visualizations that improve clinical trust. Extensive evaluations on large‐scale datasets, including Kaggle EyePACS, Messidor, and IDRiD, demonstrate that DR‐NetFusion achieves state‐of‐the‐art results with sensitivities of 97.8%, specificities of 96.7%, and a weighted F1‐score of 0.93 for DR grading. This research presents a comprehensive and highly accurate solution for DR screening, offering significant potential for early diagnosis and improved treatment strategies in ophthalmology.
  • Cervical cancer exposomics and the impact of environmental and lifestyle factors on carcinogenesis
    S. Athinarayanan, K. Dhanakodi, R. Kavitha, M. Robinson Joel, S. Athinarayanan, A.T. Rajamanickam, A. Sanjaygandhi, S. Muthukumar
    Environmental Factors in Carcinogenesis Exposome Driven Insights into Cancer Risk and Prevention, 2025
    Cervical cancer remains a significant public health concern, particularly in low- and middle-income countries. While human papillomavirus (HPV) infection is a well-established primary cause, emerging research highlights the role of environmental exposures, lifestyle factors, and socioeconomic conditions in modulating carcinogenesis. This chapter explores the concept of cancer exposomics in the context of cervical cancer, emphasizing the cumulative impact of chemical pollutants, dietary habits, occupational hazards, and lifestyle factors on disease progression. The interplay between HPV infection, environmental toxins (such as endocrine disruptors and heavy metals), and immune system modulation is discussed. Additionally, the chapter highlights the significance of early screening, vaccination, and personalized interventions in mitigating the risk. By integrating exposomic research with molecular epidemiology, this study provides insights into novel preventive and therapeutic strategies for cervical cancer management.
  • Edge computing revolution: Unleashing artificial intelligence potential in the world of edge intelligence
    Saravanan Chandrasekaran, S. Athinarayanan, M. Masthan, Anmol Kakkar, Pranav Bhatnagar, Abdul Samad
    Edge of Intelligence Exploring the Frontiers of AI at the Edge, 2025
    The emergence of Edge Intelligence (EI) is causing a revolution in the field of data processing. By incorporating potent Artificial Intelligence (AI) capabilities right at the network's edge, where data originates from devices and sensors, this approach goes beyond the constraints of conventional edge computing. Through this convergence, the latency and bandwidth limitations that come with only cloud-centric AI are overcome, enabling real-time analysis and decision-making. The following are three ways that edge intelligence encourages a paradigm shift: First, by using localized processing, it enables real-time data analysis and prompt responses. Second, latency is significantly decreased by shifting large-scale data transfers to centralized cloud resources. Third, by lessening the load on centralized systems, edge intelligence's distributed design increases infrastructure resilience and scalability and paves the way for exciting new advancements. Imagine autonomous automobiles making decisions almost instantaneously based on real-time sensor data, or smart cities utilizing edge-based analysis to improve traffic flow. The difficulty lies in the fact that robust security measures are required to safeguard data processed at the network's edge. Developing efficient AI algorithms for resource-constrained edge devices is also essential. By addressing these problems and opening the door for intelligent, nearly instantaneous decision-making at the network's edge, edge intelligence has the potential to revolutionize a wide range of sectors. While Edge Computing (EC) addressed this problem by bringing processing closer to data sources, the integration of AI at the network edge heralds in the Edge Intelligence era. This creative approach makes use of edge devices’ AI capabilities directly to allow functionality that goes beyond data processing. EI makes real-time learning, decision-making, and on-device inferencing possible at the edge of the network. Significant benefits from this integration include decreased latency, increased efficiency, and the empowerment of intelligent devices. This article addresses the need for a strong infrastructure to manage artificial intelligence (EI) and integrates cutting-edge AI models to optimize Edge Devices (ED). Motivated by the remarkable outcomes of artificial intelligence (AI) in several domains, researchers at EC are progressively delving into its possibilities, with a particular emphasis on Machine Learning (ML), a subset of AI that has experienced substantial expansion in the past few years. This page explores EC as well, including a formal description and a summary of the reasons why it is a preferred computing paradigm. Next, we look at the main issues that EC has addressed and assess the shortcomings of conventional methods. This article seeks to act as a springboard for finding new research topics that take advantage of the synergistic link between AI and EC by exhibiting research on using AI to optimize EC and applying AI inside the EC framework for additional areas.
  • Pest Detection in Plants Using Advanced Deep Learning Techniques
    Kayal Padmanandam, M. B. Shravan, Y. Divya, Ajith Sundaram, S. Athinarayanan, Kavitha Ramachandran
    Sustainable Agriculture Production Using Blockchain Technology, 2025
    Ensuring agricultural output and food security depends on pest detection in plants. Conventional approaches of pest detection are prone to human mistakes, labor-intensive, and time-consuming. New developments in deep learning methods provide reliable and effective means of real-time pest detection. This paper investigates the use of advanced deep learning models for pest detection in plants including Vision Transformers (ViTs), You Only Look Once (YOLO), and Convolutional Neural Networks (CNNs). To improve model resilience and accuracy, the suggested method makes use of a large dataset including several pest photos under different environmental settings. Metrics include precision, recall, F1-score, and detection speed guiding training and evaluation of the models. The YOLOv8 model surpasses conventional image processing and machine learning techniques in experimental findings showing the best detection accuracy. Moreover, for small datasets the combination of transfer learning and data augmentation methods greatly increases performance. Early pest detection and quick response made possible by the system's real-time capability provide a viable answer for precision farming, hence lowering pesticide use and crop losses. This study offers a basis for creating smart pest control systems, therefore supporting food security and environmentally friendly farming methods.
  • EGAN-F-MIRNet: Enlighten Generative Adversarial Network-Fusion-MIRNet for Image Enhancement of MRI Brain Image
    R. Kavitha, R. Arunadevi, K. Ishwarya, S. Athinarayanan, M. Robinson Joel, G. Manikandan
    Biomedical Materials and Devices, 2025
  • Brain Tumor Classification from MRI Scans Using a Novel CNN Architecture and Optimization Techniques
    Shaik Jaffar Hussain, B. Rupa Devi, V. Mahalakshmi, Harikala, S. Z. Parveen, S. Athinarayanan
    Communications in Computer and Information Science, 2025
  • Enhancing Power System Reliability: A Neural Network Approach for Electrical Fault Detection and Classification
    H. N. Lakshmi, Konatham Sumalatha, Anindita Kundu, V. Lavanya, R. Kavitha, S. Athinarayanan
    Lecture Notes in Networks and Systems, 2025
  • Potential applications of immersive technology in Healthcare 5.0
    Sai Anusha Veluru, Awatef Balobaid, S. Athinarayanan, Beatrice Samuel, V. Mahalakshmi, Rajesh Kumar Korupalli
    Metaverse in the Healthcare Industry Potential Applications Tools and Techniques, 2025
  • A Predictive Healthcare System for Lung Cancer Risk Using Deep Learning on Clinical Data
    LNC. Prakash K, Chittoor Bhanu Prakash, N. Badrinath, Penubaka Balaji, Mary Teresa, S. Athinarayanan
    Lecture Notes in Networks and Systems, 2025
  • Drone-Assisted SOA Routing for Stable Communication in Emergency Ad Hoc Networks
    LNC. Prakash K, G. Ramasubba Reddy, N. Badrinath, C. Nithisha, S. Athinarayanan, R. Kavitha
    Lecture Notes in Networks and Systems, 2025
  • Edge intelligence paradigm shift on optimizing the edge intelligence using artificial intelligence state-of-the-art models
    Saravanan Chandrasekaran, S. Athinarayanan, M. Masthan, Anmol Kakkar, Pranav Bhatnagar, Abdul Samad
    Advancing Intelligent Networks Through Distributed Optimization, 2024
  • COMBINING NEURAL AND SEMANTIC FEATURES IN THE ANALYSIS OF BEING SUPPORTIVE IN ONLINE FEEDBACK FROM CUSTOMERS
    R Selvi, S Athinarayanan, S Athinarayanan, V Devi, M Gobinath, Joel Robinson, P Shanthakumar
    Journal of Engineering and Technology for Industrial Applications, 2024
  • Efficient Object Detection and Segmentation Models for Drone Imagery
    Rishabh Bhagwati, Taysir Alam, Shreyansh V. Gautam, Saravanan Chandrasekaran, S Athinarayanan
    IEEE International Conference on Electronic Systems and Intelligent Computing Icesic 2024 Proceedings, 2024
  • Transforming Agriculture: A Synergistic Approach Integrating Topology with Artificial Intelligence and Machine Learning for Sustainable and Data-Driven Practice
    K.P. Sriram, P Kola Sujatha, S. Athinarayanan, G. Kanimozhi, M.Robinson Joel
    2nd International Conference on Sustainable Computing and Smart Systems Icscss 2024 Proceedings, 2024
  • Analysing various algorithms applied to Alzheimer's disease dataset to help the Future Generation
    S. Athinarayanan, K. Navaz, Tamilselvi. P, Shajeena J, Vishwa Priya V, M. Robinson Joel
    Proceedings of the 2nd International Conference on Intelligent and Innovative Technologies in Computing Electrical and Electronics Iciitcee 2024, 2024
  • Advancing Paddy Crop Productivity using Deep Learning Ensemble Approach
    S Athinarayanan, M Rudra Kumar, B Rupa Devi, Navaneeth Bhaskar, Priyanka Tupe-Waghmare, P Anjaiah
    2nd IEEE International Conference on Data Science and Information System Icdsis 2024, 2024
  • A Competency Learning and Student Centric Predictive Model for Evaluating Student Performance using Ensemble Learning
    D.Dhanya, Krishna Pramod Palekar, Harish.G, Saravanan Chandrasekaran, Hariharan T, S Athinarayanan
    IEEE International Conference on Electronic Systems and Intelligent Computing Icesic 2024 Proceedings, 2024
  • Classification of Parkinson's Disease Based on Acoustic Characteristics Using Feature Selection
    Saravanan Chandrasekaran, S. Athinarayanan, M. Masthan, Pallapothu Bhoga Venkata Ganesh, Sirigiri Sai Saran Ganesh, Mahesh T R
    2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems Adics 2024, 2024
  • Advancing Chronic Kidney Disease Diagnosis and Prediction Using a Stacked Model Approach
    N. Narendra Reddy, B Rupa Devi, B. Swathi, L. Jayasree, G. Suryanarayana, S Athinarayanan
    2024 2nd International Conference on Artificial Intelligence Trends and Pattern Recognition Icaitpr 2024, 2024
  • Effective Anatomy Learning Using Markerless Augmented Reality Interface for Medical Education
    S. Athinarayanan, M. Masthan, Saravanan Chandrasekaran, V. Ashwin Ram, Mahesh T R, Vivek V
    2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems Adics 2024, 2024
  • An Advanced Strategy for Efficient Agricultural Production using Machine Learning
    S. Athinarayanan, R Selvi, K Rajakumari, R Arunadevi, M Robinson Joel
    2nd International Conference on Automation Computing and Renewable Systems Icacrs 2023 Proceedings, 2023
  • Using Pattern Analysis and Machine Learning to Categorise users of Online Directories based on their Surfing Habits
    S. Athinarayanan, M. Robinson Joel, Shaik Jumlesha, K. Susmitha, Limgamgunta Charitha
    International Conference on Sustainable Communication Networks and Application Icscna 2023 Proceedings, 2023
  • Uncertainty-Aware Functional Analysis for Electricity Consumption Prediction Using Multi-Task Optimization Learning Model
    Saravanan Chandrasekaran, M. Masthan, Mahesh T R, S. Athinarayanan, Ashwin Ram, Vivek V
    2023 International Conference on Computer Science and Emerging Technologies Cset 2023, 2023
  • Self-Organized Multi-Hop Bridge Reservation Medium Access Control for Cyber Physical Autonomous Vehicles
    Srithar S, S.S. Sivaraju, Vetrimani E, Kanaga Priya P, S. Athinarayanan, G. Ramesh Kalyan
    2022 6th International Conference on Trends in Electronics and Informatics Icoei 2022 Proceedings, 2022
  • Robust and efficient diagnosis of cervical cancer in pap smear images using textures features with rbf and kernel SVM classification
    Arpn Journal of Engineering and Applied Sciences, 2016
  • The innovation 2d chest image segmentation for identification of tuberculosis by graph cut method
    R. Nina Shiny, B.Vasantha Chandra, S. Athinarayanan
    Proceedings of the IEEE International Conference on Soft Computing and Network Security Icsns 2015, 2015